Which model leads CharXiv Reasoning (With tools)?

Q: Which model leads CharXiv Reasoning (With tools)?

Claude Mythos 5 tops the board at 93.5

CharXiv Reasoning (With tools) Leaderboard — Model Scores

Pro Mode — raw scores, one benchmark under the lensofficial card harness

The field · 12 measured

83.293.5

12 models measured, most on the official card harness. Claude Mythos 5 tops the board at 93.5.

12 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 12Bars show 83.2–93.5 · ◆ solid = first-party or better · outlined = arm's-length

01Claude Mythos 5Anthropic93.5$10.0/M$50.0/M$0.321

02Claude Mythos PreviewAnthropic92.5———

03Claude Opus 4.7+1 altAnthropic91$5.0/M$25.0/M$0.165

04Claude Opus 4.8+2 altsAnthropic89.9$5.0/M$25.0/M$0.167

05Gemini 3.6 FlashGoogle89.4$0.75/M$3.8/M$0.025

06Gemini 3.7 FlashGoogle88.7$0.75/M$3.8/M$0.025

07Muse Spark 1.1Meta88.4$1.3/M$4.3/M$0.031

08Claude Sonnet 5Anthropic88.3$2.0/M$10.0/M$0.068

09Claude Sonnet 4.6Anthropic85.3$3.0/M$15.0/M$0.106

10Gemini 3.5 FlashGoogle84.9$1.5/M$9.0/M$0.062

11Claude Opus 4.6+1 altAnthropic84.7$5.0/M$25.0/M$0.177

12Gemini 3.1 ProGoogle83.2$2.0/M$12.0/M$0.084

◆ solid = independently verified · aggregator attested · vendor attributed — outlined = cross-reference · source-attributed. Dimmed ◆ = confidence inferred. “+N alts” = alternate disclosures in the drawer with why-demoted. Prices per million tokens; $/point = input price ÷ score. Every row opens its model dossier.

Verification: 12 models scored · 0 independently verified · 12 vendor-reported · 0 with source disagreement. How these tiers are assigned